{"id":18043471,"url":"https://github.com/fumiama/retrieval-based-voice-conversion-webui","last_synced_at":"2025-05-16T11:05:28.721Z","repository":{"id":242878070,"uuid":"810724250","full_name":"fumiama/Retrieval-based-Voice-Conversion-WebUI","owner":"fumiama","description":"Easily train a good VC model with voice data \u003c= 10 mins!","archived":false,"fork":false,"pushed_at":"2025-02-08T15:10:24.000Z","size":15449,"stargazers_count":224,"open_issues_count":24,"forks_count":24,"subscribers_count":5,"default_branch":"main","last_synced_at":"2025-04-12T08:32:50.627Z","etag":null,"topics":["audio-analysis","audio-processing","conversion","converter","rmvpe","rvc","rvc-project","vc","voice","voice-changer","voice-conversion","voicechanger","voicecloning","voiceconversion"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"agpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/fumiama.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2024-06-05T08:38:38.000Z","updated_at":"2025-04-11T23:58:31.000Z","dependencies_parsed_at":"2024-08-14T14:30:12.736Z","dependency_job_id":"ef0f5f98-b709-461f-961a-ff9f0ae377a9","html_url":"https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI","commit_stats":null,"previous_names":["fumiama/retrieval-based-voice-conversion-webui"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fumiama%2FRetrieval-based-Voice-Conversion-WebUI","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fumiama%2FRetrieval-based-Voice-Conversion-WebUI/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fumiama%2FRetrieval-based-Voice-Conversion-WebUI/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fumiama%2FRetrieval-based-Voice-Conversion-WebUI/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/fumiama","download_url":"https://codeload.github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254518384,"owners_count":22084374,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["audio-analysis","audio-processing","conversion","converter","rmvpe","rvc","rvc-project","vc","voice","voice-changer","voice-conversion","voicechanger","voicecloning","voiceconversion"],"created_at":"2024-10-30T17:08:48.042Z","updated_at":"2025-05-16T11:05:23.634Z","avatar_url":"https://github.com/fumiama.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n\n# Retrieval-based-Voice-Conversion-WebUI\nAn easy-to-use voice conversion framework based on VITS.\n\n\n\n[![madewithlove](https://img.shields.io/badge/made_with-%E2%9D%A4-red?style=for-the-badge\u0026labelColor=orange\n)](https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI)\n\n![moe](https://counter.seku.su/cmoe?name=rvc\u0026theme=r34)\n\n[![Licence](https://img.shields.io/github/license/fumiama/Retrieval-based-Voice-Conversion-WebUI?style=for-the-badge)](https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI/blob/main/LICENSE)\n[![Huggingface](https://img.shields.io/badge/🤗%20-Spaces-yellow.svg?style=for-the-badge)](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/)\n\n[![Discord](https://img.shields.io/badge/RVC%20Developers-Discord-7289DA?style=for-the-badge\u0026logo=discord\u0026logoColor=white)](https://discord.gg/HcsmBBGyVk)\n\n[**FAQ (Frequently Asked Questions)**](https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI/wiki/FAQ-(Frequently-Asked-Questions)) \n\n[**English**](./README.md) | [**中文简体**](./docs/cn/README.cn.md) | [**日本語**](./docs/jp/README.ja.md) | [**한국어**](./docs/kr/README.ko.md) ([**韓國語**](./docs/kr/README.ko.han.md)) | [**Français**](./docs/fr/README.fr.md) | [**Türkçe**](./docs/tr/README.tr.md) | [**Português**](./docs/pt/README.pt.md)\n\n\u003c/div\u003e\n\n\u003e The base model is trained using nearly 50 hours of high-quality open-source VCTK training set. Therefore, there are no copyright concerns, please feel free to use.\n\n\u003e Please look forward to the base model of RVCv3 with larger parameters, larger dataset, better effects, basically flat inference speed, and less training data required.\n\n\u003e There's a [one-click downloader](https://github.com/fumiama/RVC-Models-Downloader) for models/integration packages/tools. Welcome to try.\n\n| Training and inference Webui |\n| :--------: |\n| ![web](https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI/assets/41315874/17e48404-2627-4fad-a0ec-65f9065aeade) |\n\n| Real-time voice changing GUI |\n| :---------: |\n| ![realtime-gui](https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI/assets/41315874/95b36866-b92d-40c7-b5db-6a35ca5caeac) |\n\n## Features:\n+ Reduce tone leakage by replacing the source feature to training-set feature using top1 retrieval;\n+ Easy + fast training, even on poor graphics cards;\n+ Training with a small amounts of data (\u003e=10min low noise speech recommended);\n+ Model fusion to change timbres (using ckpt processing tab-\u003eckpt merge);\n+ Easy-to-use WebUI;\n+ UVR5 model to quickly separate vocals and instruments;\n+ High-pitch Voice Extraction Algorithm [InterSpeech2023-RMVPE](#Credits) to prevent a muted sound problem. Provides the best results (significantly) and is faster with lower resource consumption than Crepe_full;\n+ AMD/Intel graphics cards acceleration supported;\n+ Intel ARC graphics cards acceleration with IPEX supported.\n\nCheck out our [Demo Video](https://www.bilibili.com/video/BV1pm4y1z7Gm/) here!\n\n## Environment Configuration\n### Python Version Limitation\n\u003e It is recommended to use venv to manage the Python environment.\n\n\u003e For the reason of the version limitation, please refer to this [bug](https://github.com/facebookresearch/fairseq/issues/5012).\n\n```bash\npython --version # 3.8 \u003c= Python \u003c 3.11\n```\n\n### Linux/MacOS One-click Dependency Installation \u0026 Startup Script\nBy executing `run.sh` in the project root directory, you can configure the `venv` virtual environment, automatically install the required dependencies, and start the main program with one click.\n```bash\nsh ./run.sh\n```\n\n### Manual Installation of Dependencies\n1. Install `pytorch` and its core dependencies, skip if already installed. Refer to: https://pytorch.org/get-started/locally/\n\t```bash\n\tpip install torch torchvision torchaudio\n\t```\n2. If you are using Nvidia Ampere architecture (RTX30xx) in Windows, according to the experience of #21, you need to specify the cuda version corresponding to pytorch.\n\t```bash\n\tpip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu117\n\t```\n\n3. Install the corresponding dependencies according to your own graphics card.\n- Nvidia GPU\n\t```bash\n\tpip install -r requirements/main.txt\n\t```\n- AMD/Intel GPU\n\t```bash\n\tpip install -r requirements/dml.txt\n\t```\n- AMD ROCM (Linux)\n\t```bash\n\tpip install -r requirements/amd.txt\n\t```\n- Intel IPEX (Linux)\n\t```bash\n\tpip install -r requirements/ipex.txt\n\t```\n\n4.If you are using an ROCM-capable AMD Radeon GPU, then you need to choose ROCM version of PyTorch.\n\t```bash\n\tpip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm6.2\n\t```\n\n## Preparation of Other Files\n### 1. Assets\n\u003e RVC requires some models located in the `assets` folder for inference and training.\n#### Check/Download Automatically (Default)\n\u003e By default, RVC can automatically check the integrity of the required resources when the main program starts.\n\n\u003e Even if the resources are not complete, the program will continue to start.\n\n- If you want to download all resources, please add the `--update` parameter.\n- If you want to skip the resource integrity check at startup, please add the `--nocheck` parameter.\n\n#### Download Manually\n\u003e All resource files are located in [Hugging Face space](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/)\n\n\u003e You can find some scripts to download them in the `tools` folder\n\n\u003e You can also use the [one-click downloader](https://github.com/fumiama/RVC-Models-Downloader) for models/integration packages/tools\n\nBelow is a list that includes the names of all pre-models and other files required by RVC.\n\n- ./assets/hubert/hubert_base.pt\n\t```bash\n\trvcmd assets/hubert # RVC-Models-Downloader command\n\t```\n- ./assets/pretrained\n\t```bash\n\trvcmd assets/v1 # RVC-Models-Downloader command\n\t```\n- ./assets/uvr5_weights\n\t```bash\n\trvcmd assets/uvr5 # RVC-Models-Downloader command\n\t```\nIf you want to use the v2 version of the model, you need to download additional resources in\n\n- ./assets/pretrained_v2\n\t```bash\n\trvcmd assets/v2 # RVC-Models-Downloader command\n\t```\n\n### 2. Download the required files for the rmvpe vocal pitch extraction algorithm\n\nIf you want to use the latest RMVPE vocal pitch extraction algorithm, you need to download the pitch extraction model parameters and place them in `assets/rmvpe`.\n\n- [rmvpe.pt](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/rmvpe.pt)\n\t```bash\n\trvcmd assets/rmvpe # RVC-Models-Downloader command\n\t```\n\n#### Download DML environment of RMVPE (optional, for AMD/Intel GPU)\n\n- [rmvpe.onnx](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/rmvpe.onnx)\n\t```bash\n\trvcmd assets/rmvpe # RVC-Models-Downloader command\n\t```\n\n### 3. AMD ROCM (optional, Linux only)\n\nIf you want to run RVC on a Linux system based on AMD's ROCM technology, please first install the required drivers [here](https://rocm.docs.amd.com/en/latest/deploy/linux/os-native/install.html).\n\nIf you are using Arch Linux, you can use pacman to install the required drivers.\n````\npacman -S rocm-hip-sdk rocm-opencl-sdk\n````\nFor some models of graphics cards, you may need to configure the following environment variables (such as: RX6700XT).\n````\nexport ROCM_PATH=/opt/rocm #Set ROCM Executables Path\nexport HSA_OVERRIDE_GFX_VERSION=10.3.0 #Spoof GPU Model for ROCM\n````\nAlso, make sure your current user is in the `render` and `video` user groups.\n````\nsudo usermod -aG render $USERNAME\nsudo usermod -aG video $USERNAME\n````\n## Getting Started\n### Direct Launch\nUse the following command to start the WebUI.\n```bash\npython web.py\n```\n### Linux/MacOS\n```bash\n./run.sh\n```\n### For I-card users who need to use IPEX technology (Linux only)\n```bash\nsource /opt/intel/oneapi/setvars.sh\n./run.sh\n```\n### Using the Integration Package (Windows Users)\nDownload and unzip `RVC-beta.7z`. After unzipping, double-click `go-web.bat` to start the program with one click.\n```bash\nrvcmd packs/general/latest # RVC-Models-Downloader command\n```\n\n## Credits\n+ [ContentVec](https://github.com/auspicious3000/contentvec/)\n+ [VITS](https://github.com/jaywalnut310/vits)\n+ [HIFIGAN](https://github.com/jik876/hifi-gan)\n+ [Gradio](https://github.com/gradio-app/gradio)\n+ [Ultimate Vocal Remover](https://github.com/Anjok07/ultimatevocalremovergui)\n+ [audio-slicer](https://github.com/openvpi/audio-slicer)\n+ [Vocal pitch extraction:RMVPE](https://github.com/Dream-High/RMVPE)\n  + The pretrained model is trained and tested by [yxlllc](https://github.com/yxlllc/RMVPE) and [RVC-Boss](https://github.com/RVC-Boss).\n\n## Thanks to all contributors for their efforts\n[![contributors](https://contrib.rocks/image?repo=fumiama/Retrieval-based-Voice-Conversion-WebUI)](https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI/graphs/contributors)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffumiama%2Fretrieval-based-voice-conversion-webui","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffumiama%2Fretrieval-based-voice-conversion-webui","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffumiama%2Fretrieval-based-voice-conversion-webui/lists"}